Data classification using the Dempster-Shafer method

• Published in: Journal of experimental & theoretical artificial intelligence Vol. 26; no. 4; pp. 493 - 517
• Main Authors: Chen, Qi, Whitbrook, Amanda, Aickelin, Uwe, Roadknight, Chris
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 02.10.2014; Taylor & Francis Ltd
• Subjects: Algorithms; Artificial intelligence; Benchmarking; Benchmarks; Classification; data classification; Dempster's rule of combination; Dempster-Shafer Method; Dempster-Shafer theory; Design engineering; Expert systems; Mathematical analysis; Mathematical functions; Probability; Systems design; Theoretical mathematics
• ISSN: 0952-813X; 1362-3079; 1362-3079
• DOI: 10.1080/0952813X.2014.886301

In this paper, the Dempster-Shafer (D-S) method is used as the theoretical basis for creating data classification systems. Testing is carried out using three popular multiple attribute benchmark data-sets that have two, three and four classes. In each case, a subset of the available data is used for training to establish thresholds, limits or likelihoods of class membership for each attribute, and hence create mass functions that establish probability of class membership for each attribute of the test data. Classification of each data item is achieved by combination of these probabilities via Dempster's rule of combination. Results for the first two data-sets show extremely high classification accuracy that is competitive with other popular methods. The third data-set is non-numerical and difficult to classify, but good results can be achieved provided the system and mass functions are designed carefully and the right attributes are chosen for combination. In all cases, the D-S method provides comparable performance to other more popular algorithms, but the overhead of generating accurate mass functions increases the complexity with the addition of new attributes. Overall, the results suggest that the D-S approach provides a suitable framework for the design of classification systems and that automating the mass function design and calculation would increase the viability of the algorithm for complex classification problems.